Geomechanics and Engineering

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Predicting the Young's modulus of frozen sand using machine learning approaches: State-of-the-art review

  • Reza Sarkhani Benemaran (Department of Civil Engineering, Faculty of Geotechnical Engineering, University of Zanjan) ;
  • Mahzad Esmaeili-Falak (Department of Civil Engineering, North Tehran Branch, Islamic Azad University)
  • Received : 2022.12.16
  • Accepted : 2023.07.28
  • Published : 2023.09.10
⟨ Previous Next ⟩

Abstract

Accurately estimation of the geo-mechanical parameters in Artificial Ground Freezing (AGF) is a most important scientific topic in soil improvement and geotechnical engineering. In order for this, one way is using classical and conventional constitutive models based on different theories like critical state theory, Hooke's law, and so on, which are time-consuming, costly, and troublous. The others are the application of artificial intelligence (AI) techniques to predict considered parameters and behaviors accurately. This study presents a comprehensive data-mining-based model for predicting the Young's Modulus of frozen sand under the triaxial test. For this aim, several single and hybrid models were considered including additive regression, bagging, M5-Rules, M5P, random forests (RF), support vector regression (SVR), locally weighted linear (LWL), gaussian process regression (GPR), and multi-layered perceptron neural network (MLP). In the present study, cell pressure, strain rate, temperature, time, and strain were considered as the input variables, where the Young's Modulus was recognized as target. The results showed that all selected single and hybrid predicting models have acceptable agreement with measured experimental results. Especially, hybrid Additive Regression-Gaussian Process Regression and Bagging-Gaussian Process Regression have the best accuracy based on Model performance assessment criteria.

Keywords

References

  1. Akhtar, S. and Li, B. (2020), "Numerical analysis of pipeline uplift resistance in frozen clay soil considering hybrid tensile-shear yield behaviors", Int. J. Geosynthetics Ground Eng., 6(4), 1-12. https://doi.org/10.1007/s40891-020-00228-9.
  2. Alzabeebee, S., Zuhaira, A.A. andAl-Hamd, R.K.S. (2022), "Development of an optimized model to compute the undrained shaft friction adhesion factor of bored piles", Geomech. Eng., 28(4), 397-404. https://doi.org/10.12989/gae.2022.28.4.397.
  3. Andersland, O.B. and Ladanyi, B. (2013), "An introduction to frozen ground engineering", Springer Science & Business Media, https://doi.org/10.1007/978-1-4757-2290-1-3.
  4. Atkeson, C.G., Moore, A.W. and Schaal, S. (1997), "Locally weighted learning", Lazy learning, 11-73. https://doi.org/10.1007/978-94-017-2053-3.
  5. Bakermans, L. and Jamieson, B. (2009), "SWarm: A simple regression model to estimate near-surface snowpack warming for back-country avalanche forecasting", Cold Reg. Sci. Technol., 59(2-3), 133-142.  https://doi.org/10.1016/j.coldregions.2009.06.003
  6. Bayram, F. (2012), "Predicting mechanical strength loss of natural stones after freeze-thaw in cold regions", Cold Reg. Sci. Technol., 83, 98-102. https://doi.org/10.1016/j.coldregions.2012.07.003.
  7. Bean, B., Maguire, M. and Sun, Y. (2019), "Comparing design ground snow load prediction in Utah and Idaho", J. Cold Reg. Eng., 33(3), 04019010. https://doi.org/10.1061/(ASCE)CR.1943-5495.000019.
  8. Bishop, C.M. (1995), "Neural networks for pattern recognition", Oxford University Press. https://dl.acm.org/doi/10.5555/525960.
  9. Breiman, L. (1996), "Bagging predictors", Machine learning, 24(2), 123-140. https://doi.org/10.1007/BF0005865.
  10. Breiman, L. (2001), "Random forests", Machine learning, 45(1), 5-32. https://doi.org/10.1023/A:1010933404324.
  11. Chai, M., Zhang, H., Zhang, J. and Zhang, Z. (2017), "Effect of cement additives on unconfined compressive strength of warm and ice-rich frozen soil", Constr. Build. Mater., 149, 861-868. https://doi.org/10.1016/j.conbuildmat.2017.05.202.
  12. Chen, T., Morris, J. and Martin, E. (2007), "Gaussian process regression for multivariate spectroscopic calibration", Chemometrics and Intelligent Laboratory Systems, 87(1), 59-71. https://doi.org/10.1016/j.chemolab.2006.09.004
  13. Dehghanbanadaki, A., Rashid, A.S.A., Ahmad, K., Yunus, N.Z. M. and Said, K.N.M. (2022), "A computational estimation model for the subgrade reaction modulus of soil improved with DCM columns", Geomech. Eng., 28(4), 385-396. https://doi.org/10.12989/gae.2022.28.4.385.
  14. Deka, P.C. (2014), "Support vector machine applications in the field of hydrology: a review", Appl. Soft Comput., 19, 372-386. https://doi.org/10.1016/j.asoc.2014.02.002.
  15. Dawei, Y., Bing, Z., Bingbing, G., Xibo, G. and Razzaghzadeh, B. (2023), "Predicting the CPT-based pile set-up parameters using HHO-RF and PSO-RF hybrid models", Struct. Eng. Mech., 86(5), 673-686. https://doi.org/10.12989/sem.2023.86.5.673.
  16. Dinarvand, R. and Ardakani, A. (2022), "Shear behavior of geotextile-encased gravel columns in silty sand-Experimental and SVM modeling", Geomech. Eng., 28(5), 505-520. https://doi.org/10.12989/gae.2022.28.5.505.
  17. Esmaeili-Choobar, N., Esmaeili-Falak, M., Roohi-hir, M. and Keshtzad, S. (2013), "Evaluation of collapsibility potential at Talesh, Iran", Electronic J. Geotech. Eng., 18, 2561-2573.
  18. Esmaeili-Falak, M. and Hajialilue-Bonab, M. (2012), "Numerical studying the effects of gradient degree on slope stability analysis using limit equilibrium and finite element methods", Int. J. Academic Res., 4(6), 216-222. https://doi.org/10.7813/2075-4124.2012/4-4/A.30
  19. Esmaeili-Falak, M., Katebi, H. and Javadi, A. (2018), "Experimental study of the mechanical behavior of frozen soils-A case study of Tabriz subway", Periodica Polytechnica Civil Eng., 62(1), 117-125. https://doi.org/10.3311/PPci.10960.
  20. Esmaeili-Falak, M., Katebi, H., Vadiati, M. and Adamowski, J. (2019), "Predicting triaxial compressive strength and Young's modulus of frozen sand using artificial intelligence methods", J. Cold Reg. Eng., 33(3), 04019007. https://doi.org/10.1061/(ASCE)CR.1943-5495.0000188.
  21. Esmaeili-Falak, M. and Sarkhani Benemaran, R. (2023), "Ensemble deep learning-based models to predict the resilient modulus of modified base materials subjected to wet-dry cycles", Geomech. Eng., 32(6), 583-600. https://doi.org/10.12989/gae.2023.32.6.583.
  22. Esmaeili-Falak, M. and Sarkhani Benemaran, R. (2022), "Investigating the stress-strain behavior of frozen clay using triaxial test", J. Struct. Constr. Eng., https://doi.org/10.22065/JSCE.2022.332406.2747.
  23. Fei, W. and Yang, Z.J. (2019), "Modeling unconfined compression behavior of frozen Fairbanks silt considering effects of temperature, strain rate and dry density", Cold Reg. Sci. Technol., 158, 252-263. https://doi.org/10.1016/j.coldregions.2018.09.002.
  24. Frank, E. and Witten, I.H. (1998), "Generating accurate rule sets without global optimization", https://dl.acm.org/doi/10.5555/645527.657305
  25. Friedman, J.H. (2001), "Greedy function approximation: a gradient boosting machine", Annals Statistics, 1189-1232. https://doi.org/10.1214/aos/1013203451.
  26. Friedman, J.H. and Meulman, J.J. (2003), "Multiple additive regression trees with application in epidemiology", Stat. Med., 22(9), 1365-1381. https://doi.org/10.1002/sim.1501.
  27. Fu, H., Zhang, J., Huang, Z., Shi, Y. and Chen, W. (2018), "A statistical model for predicting the triaxial compressive strength of transversely isotropic rocks subjected to freeze-thaw cycling", Cold Reg. Sci. Technol., 145, 237-248. https://doi.org/10.1016/j.coldregions.2017.11.003.
  28. Ge, D.M., Zhao, L.C. and Esmaeili-Falak, M. (2022), "Estimation of rapid chloride permeability of SCC using hyperparameters optimized random forest models", J. Sustain. Cement-Based Mater., 1-19. https://doi.org/10.1080/21650373.2022.2093291.
  29. Goughnour, R.R. and Andersland, O.B. (1968), "Mechanical properties of a sand-ice system", J Soil Mech. Found. Division, 94(4), 923-950. https://doi.org/10.1061/JSFEAQ.0001179.
  30. Habibagahi, G., Katebi, S. and Johari, A. (2020), "A neural network framework for unsaturated soils", Unsaturated Soils for Asia, 107-111.
  31. Holmes, G., Hall, M. and Prank, E. (1999), "Generating rule sets from model trees", Proceedings of the Australasian joint conference on artificial intelligence, Berlin, Heidelberg. https://doi.org/10.1007/3-540-46695-9-1
  32. Hou, C., Zhu, W., Yan, B., Guan, K. and Du, J. (2020), "The effects of temperature and binder content on the behavior of frozen cemented tailings backfill at early ages", Constr. Build. Mater., 239, 117752. https://doi.org/10.1016/j.conbuildmat.2019.117752.
  33. Huang, S., Guo, Y., Liu, Y., Ke, L. and Liu, G. (2018), "Study on the influence of water flow on temperature around freeze pipes and its distribution optimization during artificial ground freezing", Appl. Therm. Eng., 135, 435-445. https://doi.org/10.1016/j.applthermaleng.2018.02.090.
  34. Jamshidi, A., Nikudel, M.R. and Khamehchiyan, M. (2013), "Predicting the long-term durability of building stones against freeze-thaw using a decay function model," Cold Reg. Sci. Technol., 92, 29-36. https://doi.org/10.1016/j.coldregions.2013.03.007.
  35. Johari, A. and Fooladi, H. (2020), "Comparative study of stochastic slope stability analysis based on conditional and unconditional random field", Comput. Geotech., 125, 103707. https://doi.org/10.1016/j.compgeo.2020.103707.
  36. Johari, A. and Fooladi, H. (2022), "Simulation of the conditional models of borehole's characteristics for slope reliability assessment", Transport. Geotech., 100778. https://doi.org/10.1016/j.trgeo.2022.100778.
  37. Johari, A. and Golkarfard, H. (2018), "Reliability analysis of unsaturated soil sites based on fundamental period throughout Shiraz, Iran", Soil Dyn. Earthq. Eng., 115, 183-197. https://doi.org/10.1016/j.soildyn.2018.08.012.
  38. Johari, A., Golkarfard, H., Davoudi, F. and Fazeli, A. (2021a), "A predictive model based on the experimental investigation of collapsible soil treatment using nano-clay in the Sivand Dam region, Iran", Bull. Eng. Geol. Environ., 80(9), 6725-6748. https://doi.org/10.1007/s10064-021-02360-w.
  39. Johari, A., Habibagahi, G. and Ghahramani, A. (2006), "Prediction of soil-water characteristic curve using genetic programming", J. Geotech. Geoenviron. Eng., 132(5), 661-665. https://doi.org/10.1061/(ASCE)1090-0241(2006)132:5(661).
  40. Johari, A., Habibagahi, G. and Ghahramani, A. (2011), "Prediction of SWCC using artificial intelligent systems: A comparative study", Scientia Iranica, 18(5), 1002-1008. https://doi.org/10.1016/j.scient.2011.09.002.
  41. Johari, A., Heydari, A. and Talebi, A. (2021b), "Prediction of discharge flow rate beneath sheet piles using scaled boundary finite element modeling database", Scientia Iranica, 28(2), 645-655. https://doi.org/10.24200/SCI.2020.53281.3158.
  42. Kim, Y., Hong, J., Shin, J. and Kim, B. (2022), "Shield TBM disc cutter replacement and wear rate prediction using machine learning techniques", Geomech. Eng., 29(3), 249-258. https://doi.org/10.12989/gae.2022.29.3.249.
  43. Kotilainen, M., Vanhatalo, J., Suominen, M. and Kujala, P. (2017), "Predicting ice-induced load amplitudes on ship bow conditional on ice thickness and ship speed in the Baltic Sea", Cold Reg. Sci. Technol., 135, 116-126. https://doi.org/10.1016/j.coldregions.2016.12.006.
  44. Kwak, N.S. and Ko, T.Y. (2022), "Machine learning-based regression analysis for estimating Cerchar abrasivity index", Geomech. Eng., 29(3), 219-228. https://doi.org/10.12989/gae.2022.29.3.219.
  45. Lawal, A.I., Kwon, S., Aladejare, A.E. and Oniyide, G.O. (2022), "Prediction of the static and dynamic mechanical properties of sedimentary rock using soft computing methods", Geomech. Eng., 28(3), 313-324. https://doi.org/10.12989/gae.2022.28.3.313.
  46. Mahmoodzadeh, A., Mohammadi, M., Abdulhamid, S.N., Ali, H. F.H., Ibrahim, H.H. and Rashidi, S. (2022a), "Forecasting tunnel path geology using Gaussian process regression", Geomech. Eng., 28(4), 359-374. https://doi.org/10.12989/gae.2022.28.4.359.
  47. Mahmoodzadeh, A., Mohammadi, M., Abdulhamid, S.N., Ibrahim, H.H., Ali, H.F.H., Nejati, H.R. and Rashidi, S. (2022b), "Prediction of duration and construction cost of road tunnels using Gaussian process regression", Geomech. Eng., 28(1), 65-75. https://doi.org/10.12989/gae.2021.28.1.065.
  48. Misra, S. and Li, H. (2019), "Noninvasive fracture characterization based on the classification of sonic wave travel times", Machine Learning for Subsurface Characterization, 243-287. https://doi.org/10.1016/C2018-0-01926-X.
  49. Mohan L,G., Rasheed, D.K. and Zachariah Koshy, D. (2019), "Experimental investigation on shear strength of artificially frozen C-Phi soil", Int. J. Adv. Res. Eng. Technol., 10(3). https://doi.org/10.34218/IJARET.10.3.2019.005.
  50. Moradi, G., Hassankhani, E. and Halabian, A.M. (2022), "Experimental and numerical analyses of buried box culverts in trenches using geofoam", Proceedings of the Institution of Civil Engineers-Geotechnical Engineering, 175(3), 311-322. https://doi.org/10.1680/jgeen.19.00288
  51. Morgan, J.N. and Sonquist, J.A. (1963), "Problems in the analysis of survey data, and a proposal", J. Am. Stat. Association, 58(302), 415-434. https://doi.org/10.2307/2283276.
  52. Nassr, A., Esmaeili-Falak, M., Katebi, H. and Javadi, A. (2018), "A new approach to modeling the behavior of frozen soils," Eng. Geol., 246, 82-90. https://doi.org/10.1016/j.enggeo.2018.09.018.
  53. Omran, B.A., Chen, Q. and Jin, R. (2016), "Comparison of data mining techniques for predicting compressive strength of environmentally friendly concrete", J. Comput Civil Eng., 30(6), 04016029. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000596.
  54. Platt, J. (1998), "Sequential minimal optimization: A fast algorithm for training support vector machines".
  55. Quinlan, J.R. (1992), "Learning with continuous classes", Proceedings of the 5th Australian joint conference on artificial intelligence, 92, 343-348. https://doi.org/10.1142/9789814536271.
  56. Rao, S.B. (1986), "Tool wear monitoring through the dynamics of stable turning". https://doi.org/10.1115/1.3187062
  57. Sarkhani Benemaran, R., Esmaeili-Falak, M. and Javadi, A. (2022), "Predicting resilient modulus of flexible pavement foundation using extreme gradient boosting based optimized models", Int. J. Pavement Eng., 1-19. https://doi.org/10.1080/10298436.2022.2095385.
  58. Sarkhani Benemaran, R., Esmaeili-Falak, M. andKatebi, H. (2022), "Physical and numerical modelling of pile-stabilised saturated layered slopes", Proceedings of the Institution of Civil Engineers-Geotechnical Engineering, 175(5), 523-538. https://doi.org/10.1680/jgeen.20.00152.
  59. Soquist, J.N. and Morgabn, J.N. (1964), "The detection of interaction effects", 35. Survey Research Center, Institute for Social Research, University of Michigan.
  60. Sun, Q. and Liu, C. (2022), "Near-explosion protection method of π-section reinforced concrete beam", Geomech. Eng., 28(3), 209-224. https://doi.org/10.12989/gae.2022.28.3.209.
  61. Torok, A., Ficsor, A., Davarpanah, M. and Vasarhelyi, B. (2019), "Comparison of mechanical properties of dry, Saturated and frozen porous rocks", Proceedings of the IAEG/AEG Annual Meeting Proceedings, San Francisco, California, Springer, Cham, 6, 113-118. https://doi.org/10.1007/978-3-319-93142-5-16
  62. Vahdani, M., Ghazavi, M. and Roustaei, M. (2020), "Prediction of mechanical properties of frozen soils using response surface method: An optimization Approach", Int. J. Eng., 33(10), 1826-1841. https://doi.org/10.5829/IJE.2020.33.10A.02.
  63. Van Eck, N.A. (1980), "Statistical analysis and data management highlights of OSIRIS IV", The American Statistician, 34(2), 119-121. https://doi.org/10.1016/0167-9473(83)90066-X .
  64. Vanthienen, J. and Wets, G. (1994), "From decision tables to expert system shells", Data & Knowledge Eng., 13(3), 265-282. https://doi.org/10.1016/0169-023X(94)00020-4.
  65. Vapnik, V. (2013), "The nature of statistical learning theory", Springer Science & Business Media. https://doi.org/10.1007/978-1-4757-3264-1
  66. Wang, B. and Chen, T. (2015), "Gaussian process regression with multiple response variables", Chemometrics and Intelligent Laboratory Systems, 142, 159-165. https://doi.org/10.1016/j.chemolab.2015.01.016.
  67. Wang, T., Ma, H., Liu, J., Luo, Q., Wang, Q. and Zhan, Y. (2021), "Assessing frost heave susceptibility of gravelly soils based on multivariate adaptive regression splines model", Cold Reg. Sci. Technol., 181, 103182. https://doi.org/10.1016/j.coldregions.2020.103182.
  68. Witten, I.H., Frank, E., Hall, M.A. and Pal, C.J. (2005), "Practical machine learning tools and techniques", Morgan Kaufmann, 578. https://doi.org/10.1016/C2009-0-19715-5 .
  69. Wood, D.M. (2003), "Geotechnical modelling (Vol. 1). CRC press. https://doi.org/10.1201/9781315273556.
  70. Yan, Y. (2022), "Resonance frequency and stability of composite micro/nanoshell via deep neural network trained by adaptive momentum-based approach", Geomech. Eng., 28(5), 477-491. https://doi.org/10.12989/gae.2022.28.5.477.
  71. Yang, X., You, Z., Hiller, J. and Watkins, D. (2017), "Correlation analysis between temperature indices and flexible pavement distress predictions using mechanistic-empirical design", J. Cold Reg. Eng., 31(4), 04017009. https://doi.org/10.1061/(ASCE)CR.1943-5495.0000135.
  72. on existing tunnels", Comput. Geotech., 121, 103477. https://doi.org/10.1016/j.compgeo.2020.103477.
  73. Zhang, G., Chen, C., Zhang, Y., Zhao, H., Wang, Y. and Wang, X. (2022), "Optimised neural network prediction of interface bond strength for GFRP tendon reinforced cemented soil", Geomech. Eng., 28(6), 599-611. https://doi.org/10.12989/gae.2022.28.6.599.
  74. Zhu, Y., Huang, L., Zhang, Z. and Bayrami, B. (2022), "Estimation of splitting tensile strength of modified recycled aggregate concrete using hybrid algorithms", Steel Compos. Struct., 44(3), 375-392. https://doi.org/10.12989/scs.2022.44.3.389.